Random Forest Classification using the Semi-Automatic Classification Plugin

This tutorial is about the Random Forest classification using the Semi-Automatic Classification Plugin (SCP) for QGIS. It is assumed that one has the basic knowledge of SCP and Basic Tutorials.

Random Forest is a particular machine learning technique, based on the iterative and random creation of decision trees (i.e. a set of rules and conditions that define a class).

WARNING: ESA SNAP is required. The ESA SNAP GPT executable must be defined in External programs settings.

The purpose of the classification is to identify the following land cover classes:

1. Water;
2. Built-up;
3. Vegetation;
4. Soil.

The following are the steps of the tutorial:

1. Input Data
2. Create the ROIs
3. Random Forest Classification

Following the video of this tutorial.

Read more »